© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 97487
    Prev
    Next
    INDEX
    Explanations

    words that indicate totality or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    all time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    么
    -0.29
     mantenido
    -0.26
     dess
    -0.24
     dejado
    -0.24
     médic
    -0.23
    准
    -0.23
     signes
    -0.22
    getSystemService
    -0.22
     élu
    -0.21
     objekt
    -0.21
    POSITIVE LOGITS
    Portail
    0.87
    transQ
    0.73
     disambiguazione
    0.72
    queryInterface
    0.70
     فريبيس
    0.68
     AssemblyProduct
    0.68
     ſehr
    0.67
    <pad>
    0.67
     Geſch
    0.66
    <unused14>
    0.66
    Activations Density 0.034%

    No Known Activations